如何使用 geom_violin 将错误框调整为小提琴图？
How to adjust error box to violin plot using geom_violin?
***编辑：
errbar_lims <- group_by(dt, together) %>%
dplyr::summarize(mean=mean(score), se=sd(score)/sqrt(n()),
upper=mean+(2*se), lower=mean-(2*se))
> dput(dt)
structure(list(ï..count = c(50L, 7L, 21L, 22L, 94L, 58L, 147L,
4L, 30L, 67L, 91L, 75L, 143L, 15L, 64L, 141L, 39L, 18L, 27L,
70L, 142L, 95L, 26L, 78L, 8L, 146L, 46L, 138L, 36L, 63L, 66L,
97L, 56L, 25L, 19L, 59L, 99L, 5L, 33L, 17L, 55L, 98L, 31L, 42L,
76L, 23L, 44L, 32L, 52L, 60L, 20L, 37L, 140L, 93L, 65L, 87L,
13L, 68L, 51L, 16L, 152L, 81L, 54L, 35L, 149L, 77L, 90L, 38L,
48L, 153L, 2L, 14L, 12L, 10L, 3L, 28L, 61L, 71L, 6L, 45L, 69L,
43L, 53L, 47L, 34L, 92L, 9L, 57L, 145L, 11L, 62L, 49L, 148L,
144L, 1L, 40L, 24L, 88L, 13L, 96L), condition = c(2L, 3L, 1L,
2L, 2L, 2L, 3L, 4L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 1L, 3L, 2L, 3L,
2L, 2L, 3L, 3L, 2L, 4L, 2L, 3L, 2L, 4L, 3L, 2L, 4L, 4L, 1L, 3L,
3L, 3L, 1L, 1L, 1L, 3L, 2L, 4L, 2L, 4L, 3L, 4L, 1L, 4L, 4L, 4L,
4L, 4L, 4L, 1L, 2L, 2L, 1L, 3L, 3L, 4L, 1L, 2L, 3L, 1L, 1L, 2L,
2L, 4L, 2L, 1L, 2L, 4L, 2L, 3L, 4L, 1L, 3L, 2L, 2L, 1L, 4L, 1L,
3L, 1L, 4L, 3L, 1L, 1L, 3L, 2L, 1L, 4L, 4L, 1L, 4L, 2L, 3L, 1L,
1L), together = structure(c(2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L), .Label = c("Shared Negative",
"Shared Positive"), class = "factor", label = "together"), second = structure(c(1L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L,
1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L,
1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L,
2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L,
2L, 1L, 1L), .Label = c("Negative Second", "Positive Second"), class = "factor"),
experimenter = c(1L, 1L, 4L, 4L, 4L, 1L, 1L, 2L, 4L, 2L,
2L, 2L, 1L, 2L, 1L, 4L, 3L, 4L, 2L, 4L, 2L, 4L, 2L, 4L, 1L,
2L, 4L, 4L, 3L, 3L, 2L, 2L, 4L, 3L, 4L, 1L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 3L, 2L, 1L, 2L, 3L, 1L, 2L, 4L, 2L, 1L, 4L, 2L,
2L, 4L, 4L, 1L, 4L, 4L, 3L, 2L, 3L, 2L, 4L, 2L, 4L, 2L, 4L,
2L, 2L, 1L, 3L, 3L, 2L, 2L, 4L, 2L, 2L, 3L, 4L, 1L, 2L, 2L,
4L, 2L, 4L, 1L, 3L, 3L, 1L, 2L, 1L, 3L, 3L, 4L, 3L, 1L, 4L
), age = structure(c(23L, 24L, 25L, 23L, 24L, 35L, 25L, 23L,
23L, 24L, 23L, 24L, 31L, 23L, 25L, 23L, 20L, 23L, 23L, 22L,
27L, 22L, 25L, 25L, 23L, 31L, 23L, 24L, 25L, 23L, 26L, 24L,
24L, 26L, 22L, 24L, 23L, 24L, 21L, 22L, 22L, 22L, 27L, 26L,
63L, 23L, 22L, 32L, 24L, 22L, 23L, 31L, 40L, 24L, 24L, 22L,
23L, 38L, 22L, 27L, 29L, 24L, 22L, 25L, 32L, 24L, 24L, 23L,
23L, 23L, 56L, 48L, 27L, 25L, 23L, 24L, 21L, 25L, 23L, 27L,
31L, 26L, 26L, 24L, 30L, 23L, 25L, 25L, 26L, 26L, 25L, 35L,
28L, 30L, 21L, 25L, 23L, 37L, 21L, 44L), label = "Age"),
sex = structure(c(2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L,
1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L
), .Label = c("Female", "Male"), class = "factor", label = "Sex"),
q1 = structure(c(0L, 11L, 18L, 0L, 18L, 19L, 9L, 13L, 36L,
41L, 29L, 34L, 33L, 53L, 27L, 35L, NA, 40L, 49L, 34L, 38L,
48L, 35L, 29L, 23L, 47L, 35L, 69L, 50L, 45L, 60L, 49L, 34L,
NA, 43L, 44L, 51L, 20L, 37L, 69L, 36L, 41L, 45L, 60L, 47L,
62L, 58L, 47L, 18L, 30L, 52L, 48L, 60L, 51L, 53L, 54L, 42L,
52L, 47L, 51L, 56L, NA, 54L, 51L, 47L, 57L, 47L, 66L, 53L,
54L, NA, 54L, 57L, 49L, 67L, 80L, 49L, 36L, 58L, 57L, 50L,
87L, 51L, 55L, 59L, 70L, 65L, 59L, 61L, 67L, 50L, 63L, 60L,
73L, 70L, 88L, 88L, 83L, 100L, 100L), label = "Question 1"),
q2 = c(0L, 13L, 12L, 22L, 23L, 19L, 31L, 11L, 71L, 13L, 36L,
12L, 33L, 24L, 37L, 37L, 37L, 41L, 50L, 35L, 58L, 39L, 42L,
37L, 64L, 48L, 44L, NA, 40L, 57L, 46L, 49L, 37L, 42L, 67L,
53L, 51L, 35L, 49L, 65L, 49L, 58L, 51L, 49L, 46L, 59L, 40L,
47L, NA, 51L, 53L, 47L, 60L, 51L, 53L, NA, 63L, 52L, 41L,
49L, 50L, NA, 53L, 52L, 64L, 54L, 57L, 50L, 57L, 54L, 55L,
64L, 62L, 27L, 65L, 70L, 53L, 68L, 65L, 54L, 59L, 53L, 61L,
56L, 58L, 69L, 74L, 62L, 56L, 67L, 62L, 58L, 60L, 72L, 78L,
100L, 84L, 96L, 100L, 99L), q3 = c(0L, 14L, 18L, NA, 19L,
16L, 53L, 66L, 81L, 35L, 36L, 65L, 32L, 73L, 75L, 30L, 64L,
44L, 13L, 51L, 62L, 50L, 42L, 51L, 47L, 12L, 60L, 62L, 66L,
77L, 55L, 43L, 69L, 70L, 85L, 68L, 50L, 56L, 46L, 97L, 67L,
80L, 59L, 63L, 46L, 60L, 35L, 47L, 35L, 52L, 48L, 58L, 62L,
51L, 65L, 67L, 65L, 61L, 71L, 58L, 56L, 57L, 54L, 73L, 60L,
62L, 57L, 63L, 53L, 54L, 79L, 87L, 59L, 61L, 78L, 16L, 43L,
81L, 69L, 69L, 58L, 47L, 49L, 56L, 58L, 51L, 77L, 65L, 61L,
67L, 83L, 90L, 81L, 83L, 78L, 66L, 98L, 9L, 71L, 100L), q4 = c(0L,
10L, 23L, 33L, 20L, 17L, 7L, 20L, 3L, 41L, 29L, 17L, 32L,
0L, 39L, 50L, 22L, 42L, 52L, 43L, 18L, 24L, 46L, 53L, 31L,
14L, 31L, 43L, 24L, 41L, 19L, 42L, 38L, 42L, 37L, 69L, 33L,
57L, 51L, 7L, 49L, 10L, 44L, 29L, 50L, 24L, 59L, 48L, 63L,
46L, 9L, 49L, 44L, 51L, 44L, 43L, 38L, 45L, 12L, 52L, 49L,
NA, 53L, 42L, 40L, 46L, 68L, 46L, 53L, 54L, 33L, 41L, 39L,
42L, 32L, 41L, 66L, 36L, 21L, 55L, 44L, 61L, 47L, 56L, 61L,
57L, 68L, 41L, 39L, 67L, 23L, 47L, 68L, 34L, 61L, 25L, 68L,
92L, 70L, 100L), q5 = c(5L, 7L, 15L, 0L, 19L, 17L, 31L, 19L,
23L, 19L, 26L, 34L, 35L, 52L, 46L, 44L, NA, 42L, 34L, 18L,
34L, 47L, 51L, 34L, 47L, 39L, 57L, 46L, 48L, 43L, 49L, 41L,
41L, 42L, 48L, 43L, 50L, 49L, 68L, 43L, 38L, 46L, 46L, 48L,
61L, 57L, 50L, 49L, 47L, 51L, NA, 48L, 34L, 51L, 52L, 52L,
46L, 54L, 48L, 55L, 57L, NA, 53L, 51L, 58L, 48L, 50L, 64L,
57L, 54L, 52L, 53L, 61L, 79L, 58L, 78L, 51L, 64L, 68L, 58L,
55L, 59L, 64L, 62L, 60L, 58L, 67L, 63L, 66L, 68L, 72L, 65L,
72L, 69L, 75L, 27L, 70L, 95L, 100L, 100L), q6 = c(3L, 13L,
14L, 43L, 17L, 23L, 0L, 20L, 11L, 33L, 38L, 3L, 44L, 0L,
6L, 50L, 0L, 46L, 34L, 53L, 34L, 19L, 50L, 43L, 47L, 63L,
46L, 27L, 18L, 42L, 42L, 41L, 51L, 32L, 43L, 24L, 50L, 52L,
11L, 4L, 49L, 31L, 59L, 28L, 61L, 46L, 56L, 50L, 40L, 51L,
30L, 47L, 57L, 46L, 46L, 44L, 43L, 42L, 53L, 50L, 50L, 53L,
53L, 66L, 30L, 40L, 52L, 39L, 52L, 54L, 51L, 32L, 32L, 64L,
43L, 7L, 58L, 31L, 39L, 51L, 57L, 44L, 59L, 62L, 61L, 57L,
32L, 39L, 68L, 58L, 83L, 62L, 43L, 32L, 61L, 65L, 60L, 94L,
86L, 100L), q7 = c(40L, 20L, 31L, 67L, 18L, 27L, 50L, 49L,
29L, 38L, 45L, 53L, 53L, 53L, 53L, 56L, 70L, 45L, 43L, 53L,
42L, 69L, 53L, 47L, 47L, 48L, 53L, 48L, 80L, 66L, 46L, 48L,
61L, 62L, 37L, 69L, 49L, 61L, 69L, 86L, 50L, 68L, 49L, 50L,
35L, 44L, 43L, 50L, 62L, 51L, 53L, 50L, 46L, 51L, 53L, 51L,
71L, 53L, 87L, 57L, 56L, 54L, 53L, 42L, 69L, 61L, 45L, 47L,
53L, 54L, 68L, 73L, 66L, 65L, 56L, 72L, 69L, 71L, 71L, 60L,
57L, 63L, 75L, 58L, 61L, 52L, 24L, 69L, 71L, 53L, 94L, 81L,
43L, 91L, 61L, 57L, 46L, 95L, 84L, 100L), q8 = c(3L, 25L,
13L, 0L, 18L, 27L, 15L, 17L, 13L, 38L, 31L, 29L, 26L, 53L,
11L, 36L, 23L, 30L, 46L, 43L, 57L, 39L, 25L, 42L, 63L, 69L,
30L, 64L, 47L, 41L, 54L, 42L, 37L, 38L, 39L, 21L, 50L, 47L,
50L, 24L, 49L, 45L, 45L, 55L, 47L, 43L, 46L, 49L, 62L, 51L,
43L, 47L, 63L, 51L, 48L, 49L, 40L, 54L, 46L, 49L, 58L, 49L,
53L, 52L, 41L, 50L, 45L, 47L, 53L, 54L, 50L, 56L, 64L, 39L,
57L, 38L, 49L, 43L, 48L, 52L, 58L, 55L, 68L, 62L, 59L, 58L,
64L, 68L, 46L, 56L, 31L, 63L, 67L, 71L, 62L, 99L, 82L, 98L,
100L, 100L), q9 = c(0L, 13L, 5L, 0L, 18L, 25L, 0L, 19L, 0L,
15L, 22L, 64L, 26L, 0L, 51L, 37L, 60L, 43L, 43L, 50L, 17L,
38L, 51L, 49L, 28L, 32L, 40L, 13L, 16L, 19L, 36L, 51L, 55L,
46L, 35L, 26L, 41L, 48L, 31L, 21L, 43L, 61L, 39L, 40L, 46L,
49L, 50L, 50L, 52L, 53L, 87L, 55L, 36L, 51L, 48L, 52L, 42L,
53L, 59L, 50L, 41L, 53L, 53L, 52L, 66L, 60L, 56L, 54L, 53L,
54L, 25L, 34L, 37L, 50L, 38L, 73L, 46L, 72L, 56L, 52L, 59L,
53L, 40L, 62L, 60L, 58L, 64L, 63L, 67L, 59L, 79L, 63L, 95L,
39L, 66L, 75L, 72L, 91L, 79L, 100L), q10 = c(0L, 2L, 3L,
0L, 18L, 25L, 21L, 17L, 22L, 31L, 24L, 16L, 26L, 53L, 37L,
16L, 53L, 40L, 50L, 40L, 61L, 49L, 34L, 44L, 34L, 69L, 47L,
37L, 66L, 24L, 49L, 50L, 35L, 42L, 37L, 56L, 50L, 52L, 66L,
65L, 51L, 41L, 45L, 62L, 46L, 42L, 49L, 50L, 61L, 53L, 69L,
48L, 38L, 51L, 48L, 50L, 69L, 53L, 65L, 58L, 58L, 53L, 53L,
51L, 58L, 57L, 59L, 60L, 53L, 54L, 74L, 48L, 68L, 69L, 52L,
74L, 65L, 47L, 59L, 56L, 67L, 57L, 70L, 61L, 59L, 67L, 63L,
70L, 66L, 53L, 75L, 65L, 72L, 100L, 67L, 100L, 78L, 98L,
100L, 100L), score = structure(c(5.1, 12.8, 15.2, 18.33,
18.8, 21.5, 21.7, 25.1, 28.9, 30.4, 31.6, 32.7, 34, 36.1,
38.2, 39.1, 41.13, 41.3, 41.4, 42, 42.1, 42.2, 42.9, 42.9,
43.1, 44.1, 44.3, 45.44, 45.5, 45.5, 45.6, 45.6, 45.8, 46.22,
47.1, 47.3, 47.5, 47.7, 47.8, 48.1, 48.1, 48.1, 48.2, 48.4,
48.5, 48.6, 48.6, 48.7, 48.89, 48.9, 49.33, 49.7, 50, 50.5,
51, 51.33, 51.9, 51.9, 52.9, 52.9, 53.1, 53.17, 53.2, 53.2,
53.3, 53.5, 53.6, 53.6, 53.7, 54, 54.11, 54.2, 54.5, 54.5,
54.6, 54.9, 54.9, 54.9, 55.4, 56.4, 56.4, 57.9, 58.4, 59,
59.6, 59.7, 59.8, 59.9, 60.1, 61.5, 65.2, 65.7, 66.1, 66.4,
67.9, 70.2, 74.6, 85.1, 89, 99.9), label = "Evaluation Score")), row.names = c(NA,
-100L), class = "data.frame")
我用箱线图创建了一个基本的小提琴图，我想添加一个错误框。这是一些代码：
dplyr::summarize(mean=mean(score), se=sd(score)/sqrt(n()),
upper=mean+(2*se), lower=mean-(2*se))
p <- ggplot() +
geom_violin(data=dt, aes(x=together, y=score, fill=second, color=second)) +
geom_point(data=errbar_lims, aes(x=together, y=mean), size=3) +
geom_errorbar(aes(x=errbar_lims$together, ymax=errbar_lims$upper,
ymin=errbar_lims$lower), stat='identity', width=.25) +
theme_minimal()
print(p)
这是我得到的：
仅显示两组的错误。
如何为所有四把小提琴添加定义错误并显示错误框？我有办法在小提琴上覆盖错误框吗？像那些：
如有任何帮助，我们将不胜感激！
您的图上总共有四把小提琴，因为您已将因子水平 together 沿 x 轴放置，并使用列 second 作为填充美学。因此，together 的每个值都有两把小提琴：一把用于“负秒”，一把用于“正秒”。
问题是当你制作数据框 errbar_lims 时，你只按 together 分组，所以如果我们检查它，我们会发现它不包含任何关于 [=15= 的信息].它只有两行，所以只能产生两个误差线：
errbar_lims
#> # A tibble: 2 x 5
#> together mean se upper lower
#> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 Shared Negative 53.3 1.92 57.1 49.4
#> 2 Shared Positive 45.3 2.00 49.3 41.3
您正在寻找的是一个包含四行的数据框，以涵盖 together 和 second 的所有 4 种可能组合。您可以通过这样做来实现：
errbar_lims <- group_by(dt, together, second) %>%
summarize(mean = mean(score),
se = sd(score) / sqrt(n()),
upper = mean + (2 * se),
lower = mean - (2 * se))
如果我们检查它，我们会看到它有四个误差线所需的四行：
errbar_lims
#> # A tibble: 4 x 6
#> # Groups: together [2]
#> together second mean se upper lower
#> <fct> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 Shared Negative Negative Second 55.7 3.35 62.4 49.0
#> 2 Shared Negative Positive Second 50.9 1.91 54.8 47.1
#> 3 Shared Positive Negative Second 45.0 3.02 51.1 39.0
#> 4 Shared Positive Positive Second 45.5 2.69 50.9 40.2
现在我们可以绘图了，但是我们需要记住告诉geom_point和geom_errorbar他们应该根据second列分组。我们还需要告诉他们我们希望 geoms 被躲避，这样它们就不会全部绘制在小提琴之间：
ggplot(dt, aes(x = together, fill = second)) +
geom_violin(aes(y = score, color = second)) +
geom_point(data = errbar_lims, aes(x = together, y = mean, group = second),
size = 3,
position = position_dodge(width = 0.9)) +
geom_errorbar(data = errbar_lims,
aes(ymax = upper, ymin = lower, group = second),
stat = 'identity',
position = position_dodge(width = 0.9),
width = 0.25) +
theme_minimal()
***编辑：
errbar_lims <- group_by(dt, together) %>%
dplyr::summarize(mean=mean(score), se=sd(score)/sqrt(n()),
upper=mean+(2*se), lower=mean-(2*se))
> dput(dt)
structure(list(ï..count = c(50L, 7L, 21L, 22L, 94L, 58L, 147L,
4L, 30L, 67L, 91L, 75L, 143L, 15L, 64L, 141L, 39L, 18L, 27L,
70L, 142L, 95L, 26L, 78L, 8L, 146L, 46L, 138L, 36L, 63L, 66L,
97L, 56L, 25L, 19L, 59L, 99L, 5L, 33L, 17L, 55L, 98L, 31L, 42L,
76L, 23L, 44L, 32L, 52L, 60L, 20L, 37L, 140L, 93L, 65L, 87L,
13L, 68L, 51L, 16L, 152L, 81L, 54L, 35L, 149L, 77L, 90L, 38L,
48L, 153L, 2L, 14L, 12L, 10L, 3L, 28L, 61L, 71L, 6L, 45L, 69L,
43L, 53L, 47L, 34L, 92L, 9L, 57L, 145L, 11L, 62L, 49L, 148L,
144L, 1L, 40L, 24L, 88L, 13L, 96L), condition = c(2L, 3L, 1L,
2L, 2L, 2L, 3L, 4L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 1L, 3L, 2L, 3L,
2L, 2L, 3L, 3L, 2L, 4L, 2L, 3L, 2L, 4L, 3L, 2L, 4L, 4L, 1L, 3L,
3L, 3L, 1L, 1L, 1L, 3L, 2L, 4L, 2L, 4L, 3L, 4L, 1L, 4L, 4L, 4L,
4L, 4L, 4L, 1L, 2L, 2L, 1L, 3L, 3L, 4L, 1L, 2L, 3L, 1L, 1L, 2L,
2L, 4L, 2L, 1L, 2L, 4L, 2L, 3L, 4L, 1L, 3L, 2L, 2L, 1L, 4L, 1L,
3L, 1L, 4L, 3L, 1L, 1L, 3L, 2L, 1L, 4L, 4L, 1L, 4L, 2L, 3L, 1L,
1L), together = structure(c(2L, 2L, 1L, 2L, 2L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 2L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L,
2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L,
1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L,
2L, 2L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 1L,
2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 1L), .Label = c("Shared Negative",
"Shared Positive"), class = "factor", label = "together"), second = structure(c(1L,
2L, 1L, 1L, 1L, 1L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L,
1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 2L,
1L, 2L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 2L, 1L, 2L, 1L, 1L, 1L,
2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 2L, 1L, 1L, 2L, 2L, 1L, 2L, 1L,
2L, 1L, 1L), .Label = c("Negative Second", "Positive Second"), class = "factor"),
experimenter = c(1L, 1L, 4L, 4L, 4L, 1L, 1L, 2L, 4L, 2L,
2L, 2L, 1L, 2L, 1L, 4L, 3L, 4L, 2L, 4L, 2L, 4L, 2L, 4L, 1L,
2L, 4L, 4L, 3L, 3L, 2L, 2L, 4L, 3L, 4L, 1L, 2L, 2L, 1L, 2L,
2L, 2L, 2L, 3L, 2L, 1L, 2L, 3L, 1L, 2L, 4L, 2L, 1L, 4L, 2L,
2L, 4L, 4L, 1L, 4L, 4L, 3L, 2L, 3L, 2L, 4L, 2L, 4L, 2L, 4L,
2L, 2L, 1L, 3L, 3L, 2L, 2L, 4L, 2L, 2L, 3L, 4L, 1L, 2L, 2L,
4L, 2L, 4L, 1L, 3L, 3L, 1L, 2L, 1L, 3L, 3L, 4L, 3L, 1L, 4L
), age = structure(c(23L, 24L, 25L, 23L, 24L, 35L, 25L, 23L,
23L, 24L, 23L, 24L, 31L, 23L, 25L, 23L, 20L, 23L, 23L, 22L,
27L, 22L, 25L, 25L, 23L, 31L, 23L, 24L, 25L, 23L, 26L, 24L,
24L, 26L, 22L, 24L, 23L, 24L, 21L, 22L, 22L, 22L, 27L, 26L,
63L, 23L, 22L, 32L, 24L, 22L, 23L, 31L, 40L, 24L, 24L, 22L,
23L, 38L, 22L, 27L, 29L, 24L, 22L, 25L, 32L, 24L, 24L, 23L,
23L, 23L, 56L, 48L, 27L, 25L, 23L, 24L, 21L, 25L, 23L, 27L,
31L, 26L, 26L, 24L, 30L, 23L, 25L, 25L, 26L, 26L, 25L, 35L,
28L, 30L, 21L, 25L, 23L, 37L, 21L, 44L), label = "Age"),
sex = structure(c(2L, 2L, 1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L,
1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L,
1L, 1L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 2L, 1L,
1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 1L, 1L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 2L, 2L, 2L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L,
1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 1L, 2L, 1L, 1L
), .Label = c("Female", "Male"), class = "factor", label = "Sex"),
q1 = structure(c(0L, 11L, 18L, 0L, 18L, 19L, 9L, 13L, 36L,
41L, 29L, 34L, 33L, 53L, 27L, 35L, NA, 40L, 49L, 34L, 38L,
48L, 35L, 29L, 23L, 47L, 35L, 69L, 50L, 45L, 60L, 49L, 34L,
NA, 43L, 44L, 51L, 20L, 37L, 69L, 36L, 41L, 45L, 60L, 47L,
62L, 58L, 47L, 18L, 30L, 52L, 48L, 60L, 51L, 53L, 54L, 42L,
52L, 47L, 51L, 56L, NA, 54L, 51L, 47L, 57L, 47L, 66L, 53L,
54L, NA, 54L, 57L, 49L, 67L, 80L, 49L, 36L, 58L, 57L, 50L,
87L, 51L, 55L, 59L, 70L, 65L, 59L, 61L, 67L, 50L, 63L, 60L,
73L, 70L, 88L, 88L, 83L, 100L, 100L), label = "Question 1"),
q2 = c(0L, 13L, 12L, 22L, 23L, 19L, 31L, 11L, 71L, 13L, 36L,
12L, 33L, 24L, 37L, 37L, 37L, 41L, 50L, 35L, 58L, 39L, 42L,
37L, 64L, 48L, 44L, NA, 40L, 57L, 46L, 49L, 37L, 42L, 67L,
53L, 51L, 35L, 49L, 65L, 49L, 58L, 51L, 49L, 46L, 59L, 40L,
47L, NA, 51L, 53L, 47L, 60L, 51L, 53L, NA, 63L, 52L, 41L,
49L, 50L, NA, 53L, 52L, 64L, 54L, 57L, 50L, 57L, 54L, 55L,
64L, 62L, 27L, 65L, 70L, 53L, 68L, 65L, 54L, 59L, 53L, 61L,
56L, 58L, 69L, 74L, 62L, 56L, 67L, 62L, 58L, 60L, 72L, 78L,
100L, 84L, 96L, 100L, 99L), q3 = c(0L, 14L, 18L, NA, 19L,
16L, 53L, 66L, 81L, 35L, 36L, 65L, 32L, 73L, 75L, 30L, 64L,
44L, 13L, 51L, 62L, 50L, 42L, 51L, 47L, 12L, 60L, 62L, 66L,
77L, 55L, 43L, 69L, 70L, 85L, 68L, 50L, 56L, 46L, 97L, 67L,
80L, 59L, 63L, 46L, 60L, 35L, 47L, 35L, 52L, 48L, 58L, 62L,
51L, 65L, 67L, 65L, 61L, 71L, 58L, 56L, 57L, 54L, 73L, 60L,
62L, 57L, 63L, 53L, 54L, 79L, 87L, 59L, 61L, 78L, 16L, 43L,
81L, 69L, 69L, 58L, 47L, 49L, 56L, 58L, 51L, 77L, 65L, 61L,
67L, 83L, 90L, 81L, 83L, 78L, 66L, 98L, 9L, 71L, 100L), q4 = c(0L,
10L, 23L, 33L, 20L, 17L, 7L, 20L, 3L, 41L, 29L, 17L, 32L,
0L, 39L, 50L, 22L, 42L, 52L, 43L, 18L, 24L, 46L, 53L, 31L,
14L, 31L, 43L, 24L, 41L, 19L, 42L, 38L, 42L, 37L, 69L, 33L,
57L, 51L, 7L, 49L, 10L, 44L, 29L, 50L, 24L, 59L, 48L, 63L,
46L, 9L, 49L, 44L, 51L, 44L, 43L, 38L, 45L, 12L, 52L, 49L,
NA, 53L, 42L, 40L, 46L, 68L, 46L, 53L, 54L, 33L, 41L, 39L,
42L, 32L, 41L, 66L, 36L, 21L, 55L, 44L, 61L, 47L, 56L, 61L,
57L, 68L, 41L, 39L, 67L, 23L, 47L, 68L, 34L, 61L, 25L, 68L,
92L, 70L, 100L), q5 = c(5L, 7L, 15L, 0L, 19L, 17L, 31L, 19L,
23L, 19L, 26L, 34L, 35L, 52L, 46L, 44L, NA, 42L, 34L, 18L,
34L, 47L, 51L, 34L, 47L, 39L, 57L, 46L, 48L, 43L, 49L, 41L,
41L, 42L, 48L, 43L, 50L, 49L, 68L, 43L, 38L, 46L, 46L, 48L,
61L, 57L, 50L, 49L, 47L, 51L, NA, 48L, 34L, 51L, 52L, 52L,
46L, 54L, 48L, 55L, 57L, NA, 53L, 51L, 58L, 48L, 50L, 64L,
57L, 54L, 52L, 53L, 61L, 79L, 58L, 78L, 51L, 64L, 68L, 58L,
55L, 59L, 64L, 62L, 60L, 58L, 67L, 63L, 66L, 68L, 72L, 65L,
72L, 69L, 75L, 27L, 70L, 95L, 100L, 100L), q6 = c(3L, 13L,
14L, 43L, 17L, 23L, 0L, 20L, 11L, 33L, 38L, 3L, 44L, 0L,
6L, 50L, 0L, 46L, 34L, 53L, 34L, 19L, 50L, 43L, 47L, 63L,
46L, 27L, 18L, 42L, 42L, 41L, 51L, 32L, 43L, 24L, 50L, 52L,
11L, 4L, 49L, 31L, 59L, 28L, 61L, 46L, 56L, 50L, 40L, 51L,
30L, 47L, 57L, 46L, 46L, 44L, 43L, 42L, 53L, 50L, 50L, 53L,
53L, 66L, 30L, 40L, 52L, 39L, 52L, 54L, 51L, 32L, 32L, 64L,
43L, 7L, 58L, 31L, 39L, 51L, 57L, 44L, 59L, 62L, 61L, 57L,
32L, 39L, 68L, 58L, 83L, 62L, 43L, 32L, 61L, 65L, 60L, 94L,
86L, 100L), q7 = c(40L, 20L, 31L, 67L, 18L, 27L, 50L, 49L,
29L, 38L, 45L, 53L, 53L, 53L, 53L, 56L, 70L, 45L, 43L, 53L,
42L, 69L, 53L, 47L, 47L, 48L, 53L, 48L, 80L, 66L, 46L, 48L,
61L, 62L, 37L, 69L, 49L, 61L, 69L, 86L, 50L, 68L, 49L, 50L,
35L, 44L, 43L, 50L, 62L, 51L, 53L, 50L, 46L, 51L, 53L, 51L,
71L, 53L, 87L, 57L, 56L, 54L, 53L, 42L, 69L, 61L, 45L, 47L,
53L, 54L, 68L, 73L, 66L, 65L, 56L, 72L, 69L, 71L, 71L, 60L,
57L, 63L, 75L, 58L, 61L, 52L, 24L, 69L, 71L, 53L, 94L, 81L,
43L, 91L, 61L, 57L, 46L, 95L, 84L, 100L), q8 = c(3L, 25L,
13L, 0L, 18L, 27L, 15L, 17L, 13L, 38L, 31L, 29L, 26L, 53L,
11L, 36L, 23L, 30L, 46L, 43L, 57L, 39L, 25L, 42L, 63L, 69L,
30L, 64L, 47L, 41L, 54L, 42L, 37L, 38L, 39L, 21L, 50L, 47L,
50L, 24L, 49L, 45L, 45L, 55L, 47L, 43L, 46L, 49L, 62L, 51L,
43L, 47L, 63L, 51L, 48L, 49L, 40L, 54L, 46L, 49L, 58L, 49L,
53L, 52L, 41L, 50L, 45L, 47L, 53L, 54L, 50L, 56L, 64L, 39L,
57L, 38L, 49L, 43L, 48L, 52L, 58L, 55L, 68L, 62L, 59L, 58L,
64L, 68L, 46L, 56L, 31L, 63L, 67L, 71L, 62L, 99L, 82L, 98L,
100L, 100L), q9 = c(0L, 13L, 5L, 0L, 18L, 25L, 0L, 19L, 0L,
15L, 22L, 64L, 26L, 0L, 51L, 37L, 60L, 43L, 43L, 50L, 17L,
38L, 51L, 49L, 28L, 32L, 40L, 13L, 16L, 19L, 36L, 51L, 55L,
46L, 35L, 26L, 41L, 48L, 31L, 21L, 43L, 61L, 39L, 40L, 46L,
49L, 50L, 50L, 52L, 53L, 87L, 55L, 36L, 51L, 48L, 52L, 42L,
53L, 59L, 50L, 41L, 53L, 53L, 52L, 66L, 60L, 56L, 54L, 53L,
54L, 25L, 34L, 37L, 50L, 38L, 73L, 46L, 72L, 56L, 52L, 59L,
53L, 40L, 62L, 60L, 58L, 64L, 63L, 67L, 59L, 79L, 63L, 95L,
39L, 66L, 75L, 72L, 91L, 79L, 100L), q10 = c(0L, 2L, 3L,
0L, 18L, 25L, 21L, 17L, 22L, 31L, 24L, 16L, 26L, 53L, 37L,
16L, 53L, 40L, 50L, 40L, 61L, 49L, 34L, 44L, 34L, 69L, 47L,
37L, 66L, 24L, 49L, 50L, 35L, 42L, 37L, 56L, 50L, 52L, 66L,
65L, 51L, 41L, 45L, 62L, 46L, 42L, 49L, 50L, 61L, 53L, 69L,
48L, 38L, 51L, 48L, 50L, 69L, 53L, 65L, 58L, 58L, 53L, 53L,
51L, 58L, 57L, 59L, 60L, 53L, 54L, 74L, 48L, 68L, 69L, 52L,
74L, 65L, 47L, 59L, 56L, 67L, 57L, 70L, 61L, 59L, 67L, 63L,
70L, 66L, 53L, 75L, 65L, 72L, 100L, 67L, 100L, 78L, 98L,
100L, 100L), score = structure(c(5.1, 12.8, 15.2, 18.33,
18.8, 21.5, 21.7, 25.1, 28.9, 30.4, 31.6, 32.7, 34, 36.1,
38.2, 39.1, 41.13, 41.3, 41.4, 42, 42.1, 42.2, 42.9, 42.9,
43.1, 44.1, 44.3, 45.44, 45.5, 45.5, 45.6, 45.6, 45.8, 46.22,
47.1, 47.3, 47.5, 47.7, 47.8, 48.1, 48.1, 48.1, 48.2, 48.4,
48.5, 48.6, 48.6, 48.7, 48.89, 48.9, 49.33, 49.7, 50, 50.5,
51, 51.33, 51.9, 51.9, 52.9, 52.9, 53.1, 53.17, 53.2, 53.2,
53.3, 53.5, 53.6, 53.6, 53.7, 54, 54.11, 54.2, 54.5, 54.5,
54.6, 54.9, 54.9, 54.9, 55.4, 56.4, 56.4, 57.9, 58.4, 59,
59.6, 59.7, 59.8, 59.9, 60.1, 61.5, 65.2, 65.7, 66.1, 66.4,
67.9, 70.2, 74.6, 85.1, 89, 99.9), label = "Evaluation Score")), row.names = c(NA,
-100L), class = "data.frame")
我用箱线图创建了一个基本的小提琴图，我想添加一个错误框。这是一些代码：
dplyr::summarize(mean=mean(score), se=sd(score)/sqrt(n()),
upper=mean+(2*se), lower=mean-(2*se))
p <- ggplot() +
geom_violin(data=dt, aes(x=together, y=score, fill=second, color=second)) +
geom_point(data=errbar_lims, aes(x=together, y=mean), size=3) +
geom_errorbar(aes(x=errbar_lims$together, ymax=errbar_lims$upper,
ymin=errbar_lims$lower), stat='identity', width=.25) +
theme_minimal()
print(p)
这是我得到的：
仅显示两组的错误。
如何为所有四把小提琴添加定义错误并显示错误框？我有办法在小提琴上覆盖错误框吗？像那些：
如有任何帮助，我们将不胜感激！
您的图上总共有四把小提琴，因为您已将因子水平 together 沿 x 轴放置，并使用列 second 作为填充美学。因此，together 的每个值都有两把小提琴：一把用于“负秒”，一把用于“正秒”。
问题是当你制作数据框 errbar_lims 时，你只按 together 分组，所以如果我们检查它，我们会发现它不包含任何关于 [=15= 的信息].它只有两行，所以只能产生两个误差线：
errbar_lims
#> # A tibble: 2 x 5
#> together mean se upper lower
#> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 Shared Negative 53.3 1.92 57.1 49.4
#> 2 Shared Positive 45.3 2.00 49.3 41.3
您正在寻找的是一个包含四行的数据框，以涵盖 together 和 second 的所有 4 种可能组合。您可以通过这样做来实现：
errbar_lims <- group_by(dt, together, second) %>%
summarize(mean = mean(score),
se = sd(score) / sqrt(n()),
upper = mean + (2 * se),
lower = mean - (2 * se))
如果我们检查它，我们会看到它有四个误差线所需的四行：
errbar_lims
#> # A tibble: 4 x 6
#> # Groups: together [2]
#> together second mean se upper lower
#> <fct> <fct> <dbl> <dbl> <dbl> <dbl>
#> 1 Shared Negative Negative Second 55.7 3.35 62.4 49.0
#> 2 Shared Negative Positive Second 50.9 1.91 54.8 47.1
#> 3 Shared Positive Negative Second 45.0 3.02 51.1 39.0
#> 4 Shared Positive Positive Second 45.5 2.69 50.9 40.2
现在我们可以绘图了，但是我们需要记住告诉geom_point和geom_errorbar他们应该根据second列分组。我们还需要告诉他们我们希望 geoms 被躲避，这样它们就不会全部绘制在小提琴之间：
ggplot(dt, aes(x = together, fill = second)) +
geom_violin(aes(y = score, color = second)) +
geom_point(data = errbar_lims, aes(x = together, y = mean, group = second),
size = 3,
position = position_dodge(width = 0.9)) +
geom_errorbar(data = errbar_lims,
aes(ymax = upper, ymin = lower, group = second),
stat = 'identity',
position = position_dodge(width = 0.9),
width = 0.25) +
theme_minimal()